Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

DART: Detect Anything in Real Time Detect Anything in Real Time: Real-time object detection using frontier object detection models. Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.

rsasaki0109's profile picture

Ryohei Sasaki@engineer

10,738 subscribers

34,093 Aufrufe • vor 13 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:
2:31

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:

Joseph Nelson

18,231 Aufrufe • vor 1 Jahr

Detect objects in videos locally on iPhone using Roboflow's real-time detection transformer (RF-DETR) in SwiftUI + Core AI. Run the model on iOS for free, no API calls.👇 - - -
0:31

Detect objects in videos locally on iPhone using Roboflow's real-time detection transformer (RF-DETR) in SwiftUI + Core AI. Run the model on iOS for free, no API calls.👇 - - -

Amos Gyamfi

12,986 Aufrufe • vor 1 Monat

This is huge for video AI. Stream dropped Vision Agents, an open-source framework that lets AI watch and understand live video in real-time. - Sports coaching - Real-time threat detection - Live meeting assistants Combines YOLO, Gemini, OpenAI. Free. Open-source 🧵👇
0:21

This is huge for video AI. Stream dropped Vision Agents, an open-source framework that lets AI watch and understand live video in real-time. - Sports coaching - Real-time threat detection - Live meeting assistants Combines YOLO, Gemini, OpenAI. Free. Open-source 🧵👇

Alvaro Cintas

85,488 Aufrufe • vor 8 Monaten

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"
0:24

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"

AA

28,753 Aufrufe • vor 5 Monaten

Whoa, this is Temporal Gaussian Hierarchy (TGH). This AI can real-time render long volumetric videos in 1080p at 450 fps on a single RTX 4090 GPU. And 18,000 frames (around 10 minutes) long 🤯 7 wild demos: 1. Real-time demos on MobileStage dataset
0:52

Whoa, this is Temporal Gaussian Hierarchy (TGH). This AI can real-time render long volumetric videos in 1080p at 450 fps on a single RTX 4090 GPU. And 18,000 frames (around 10 minutes) long 🤯 7 wild demos: 1. Real-time demos on MobileStage dataset

Min Choi

464,149 Aufrufe • vor 1 Jahr

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2
0:27

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

AA

72,555 Aufrufe • vor 6 Monaten

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.
0:23

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

29,029 Aufrufe • vor 7 Monaten

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.
1:33

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

28,871 Aufrufe • vor 8 Monaten

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.
0:39

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

15,968 Aufrufe • vor 7 Monaten

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇
0:42

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇

Xenova

77,179 Aufrufe • vor 6 Monaten

Gemini only flags generated content that includes synthID, which means it has to come from Google's own tools. Resemble AI doesn't have that limitation. It can detect deepfakes across videos, audios, and images, no matter what models created them. Powered by Detect-3B Omni and Gemini 3.0 Flash, Resemble Intelligence delivers forensic-grade deepfake detection in near-real time!
0:28

Gemini only flags generated content that includes synthID, which means it has to come from Google's own tools. Resemble AI doesn't have that limitation. It can detect deepfakes across videos, audios, and images, no matter what models created them. Powered by Detect-3B Omni and Gemini 3.0 Flash, Resemble Intelligence delivers forensic-grade deepfake detection in near-real time!

Dev Shah

11,539 Aufrufe • vor 8 Monaten

Just dropped two new tools in Score Studio today: → Real-time depth estimation + object detection on the same frame. → Background removal. Next… 3D point clouds Score Studio is going to become the go-to platform for anything vision: ✅ Auto-Data Generation ✅ Auto-Training ✅ Auto-Evals ✅ Auto-Deploy All battle-tested by miners. All powered by Bittensor.
0:14

Just dropped two new tools in Score Studio today: → Real-time depth estimation + object detection on the same frame. → Background removal. Next… 3D point clouds Score Studio is going to become the go-to platform for anything vision: ✅ Auto-Data Generation ✅ Auto-Training ✅ Auto-Evals ✅ Auto-Deploy All battle-tested by miners. All powered by Bittensor.

Score

16,638 Aufrufe • vor 24 Tagen

planking for penguins 🐧 a real-time exercise tracking game, coded with Grok 4 (xAI) this uses mediapipe AI vision to detect when the player has proper plank form (knees-hips-shoulders in a horizontal line, elbows low) also using Three.js for visuals and tonejs for audio this all runs in real-time in the browser, using a regular laptop + webcam 🔗 live demo below
0:40

planking for penguins 🐧 a real-time exercise tracking game, coded with Grok 4 (xAI) this uses mediapipe AI vision to detect when the player has proper plank form (knees-hips-shoulders in a horizontal line, elbows low) also using Three.js for visuals and tonejs for audio this all runs in real-time in the browser, using a regular laptop + webcam 🔗 live demo below

AA

244,071 Aufrufe • vor 1 Jahr

🚀 We open-sourced LongLive — interactive, real-time long-video generation. 👥Generates video in real time as users enter text prompts. ⚡️20.7 FPS on a single H100,⏱️up to 240s per clip. 🎬Fine-tunes SOTA short-video models (e.g., Wan) into long-video generators. 🌍One step closer to World Models. All code for training & inference, model weights, demo page, and videos released! Paper: Code: Model: Demo Page: Introduction Video:
3:18

🚀 We open-sourced LongLive — interactive, real-time long-video generation. 👥Generates video in real time as users enter text prompts. ⚡️20.7 FPS on a single H100,⏱️up to 240s per clip. 🎬Fine-tunes SOTA short-video models (e.g., Wan) into long-video generators. 🌍One step closer to World Models. All code for training & inference, model weights, demo page, and videos released! Paper: Code: Model: Demo Page: Introduction Video:

Yukang Chen

11,939 Aufrufe • vor 11 Monaten

We present MotionStream — real-time, long-duration video generation that you can interactively control just by dragging your mouse. All videos here are raw, real-time screen captures without any post-processing. Model runs on a single H100 at 29 FPS and 0.4s latency.
0:42

We present MotionStream — real-time, long-duration video generation that you can interactively control just by dragging your mouse. All videos here are raw, real-time screen captures without any post-processing. Model runs on a single H100 at 29 FPS and 0.4s latency.

Xun Huang

98,924 Aufrufe • vor 10 Monaten

🕹️ The way of creating anything in real time with LCM-LoRA technology is so natural that it's here to stay. That's for sure! 💡 This is just a quick test I did using Krea to build an RPG dungeon. Imagine creating a video game in REAL TIME!
0:55

🕹️ The way of creating anything in real time with LCM-LoRA technology is so natural that it's here to stay. That's for sure! 💡 This is just a quick test I did using Krea to build an RPG dungeon. Imagine creating a video game in REAL TIME!

Javi Lopez ⛩️

164,254 Aufrufe • vor 2 Jahren

Introducing SOS🚨: a wearable that saves your life 🛟 It will automatically detect when you’re in danger and send real time alerts to emergency contacts. And it’s fully open source. Link 👇
0:38

Introducing SOS🚨: a wearable that saves your life 🛟 It will automatically detect when you’re in danger and send real time alerts to emergency contacts. And it’s fully open source. Link 👇

shrey birmiwal

12,668 Aufrufe • vor 1 Jahr

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.
0:54

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

Runway

1,164,245 Aufrufe • vor 5 Monaten

"near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence [...] a Neural Object Field that is learned concurrently with a pose graph optimization process in order to robustly accumulate information into a consistent 3D representation"
0:53

"near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence [...] a Neural Object Field that is learned concurrently with a pose graph optimization process in order to robustly accumulate information into a consistent 3D representation"

Fabien Benetou

222,937 Aufrufe • vor 3 Jahren